Long-Horizon LLM Agents

LLM: Large Language Model

Long-horizon LLM agents are systems designed to pursue goals through many connected actions, often while using tools and responding to changing information. Common approaches include hierarchical planning and subgoals, reinforcement learning with step-level or milestone rewards, persistent memory and context compression, and harnesses that verify actions and recover from errors. Researchers evaluate them in interactive settings such as ALFWorld, WebShop, ScienceWorld, WebArena, software-engineering benchmarks, and deep-research tasks. A central challenge is making performance reliable over time: errors and lost constraints can compound, while memory, verification, and extra computation can improve success but add cost or introduce new failure modes.

Latest papers

451 papers92 papers in the last four weeks, up 56% on the four weeks before. 0.5% of all new papers.

Scaling Test-Time Compute for Agentic Coding
Apr 16, 2026Joongwon Kim, Wannan Yang, Kelvin Niu +13AI Coding Agents Test-Time Scaling
1Meta Superintelligence Labs · University of Washington · 3New York University +4
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization
Apr 15, 2026Zhengxi Lu, Fei Tang, Guangyi Liu +8Long-Horizon LLM Agents Mobile GUI Automation
Zhejiang University · Apple · Tencent
WebXSkill: Skill Learning for Autonomous Web Agents
Apr 14, 2026Zhaoyang Wang, Qianhui Wu, Xuchao Zhang +12LLM Agent Skill Learning Long-Horizon LLM Agents
University of North Carolina at Chapel Hill · Microsoft
Toward Autonomous Long-Horizon Engineering for ML Research
Apr 14, 2026Guoxin Chen, Jie Chen, Lei Chen +7Long-Horizon LLM Agents Multi-Agent LLM Systems
Towards Long-horizon Agentic Multimodal Search
Apr 14, 2026Yifan Du, Zikang Liu, Jinbiao Peng +5Multimodal Search Agents Long-Horizon LLM Agents
Gaoling School of Artificial Intelligence, Renmin University of China. · City University of Hong Kong.
QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence
Apr 14, 2026Zhichao Lin, Zhichao Liang, Gaoqiang Liu +6Agentic Search LLM Agent Training
Qwen Applications Business Group, Alibaba · Shanghai Jiao Tong University
EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
Apr 14, 2026Shiyu He, Minchi Kuang, Mengxian Wang +2Large Language Model-Based Role-Play Simulation Interactive Storytelling
School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China · Department of Precision Instrument, Tsinghua University, Beijing 100084, China
Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
Apr 13, 2026Rongzhe Wei, Ge Shi, Min Cheng +5Uncertainty-Aware Exploration LLM Agent Planning
Georgia Institute of Technology · Amazon
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Apr 13, 2026Yoonsang Lee, Howard Yen, Xi Ye +1Test-Time Scaling Long-Horizon Agent Tasks
Princeton Language and Intelligence, Princeton University
Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
Apr 13, 2026Xiaozhe Li, Tianyi Lyu, Yizhao Yang +6Lost-in-the-Middle Effect LLM Context Management
Tongji University · CurrentsAI Research · Stanford University +1
FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks
Apr 11, 2026Yupeng Cao, Haohang Li, Weijin Liu +11Agent Trajectory Analysis LLM Tool Use
Stevens Institute of Technology · Independent Researcher · The FinAI +2
SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation
Apr 10, 2026Han Luo, Guy LabanMulti-Turn Dialogue Management Large Language Model-Based Role-Play Simulation
University of Leeds · Southwest Jiaotong University · Ben-Gurion University of the Negev +1
Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents
Apr 9, 2026Khushal SethiInference-Time Compute Allocation LLM Inference Efficiency
Stanford University
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
Apr 9, 2026Zhifei Xie, Zongzheng Hu, Fangda Ye +10Proactive Agents Agentic AI
NTU · Pask-Core · NUS
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
Apr 7, 2026Shuai Zhen, Yanhua Yu, Ruopei Guo +2RL for LLM Agents Reinforcement Learning
Beijing University of Posts and Telecommunications · China Mobile Group Design Institute Co., Ltd · Singapore Management University
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Apr 6, 2026Chenxi Wang, Zhuoyun Yu, Xin Xie +8LLM Agent Skill Learning LLM Agents
1Zhejiang University · 2Ant Digital Technologies, Ant Group.
Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception
Apr 6, 2026Seamus BradyLLM Agents Long-Horizon LLM Agents
Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents
Apr 3, 2026Bin Wen, Ruoxuan Zhang, Yang Chen +2Long-Horizon LLM Agents Memory-Augmented Language Model Agents
Nanjing University · Jilin University
ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
Apr 2, 2026Yong Wu, YanZhao Zheng, TianZe Xu +9LLM Context Management Long-Horizon LLM Agents
Zhejiang University, Hangzhou, China · Alibaba Group, Hangzhou, China
Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
Mar 31, 2026Ashish Rana, Chia-Chien Hung, Qumeng Sun +2Long-Horizon LLM Agents Agent Memory Management
NEC Laboratories Europe, Heidelberg, Germany · GWDG, Georg-August-Universität Göttingen, Göttingen, Germany
Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents
Mar 31, 2026Aaditya Khanal, Yangyang Tao, Junxiu ZhouLLM Reliability LLM Agent Reliability
School of Computing and Analytics, Northern Kentucky University
CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments
Mar 30, 2026Yi Yu, Guangquan Hu, Chenghuang Shen +15LLM Agent Efficiency LLM Agent Evaluation
School of Mathematics and Sciences, Fudan University, Shanghai, China · Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China · Shanghai Center for Mathematical Sciences, Fudan University, Shanghai, China +2
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Mar 29, 2026Zhaopeng Feng, Liangcai Su, Zhen Zhang +16LLM Context Management Long-Horizon LLM Agents
Tongyi Lab, Alibaba Group
AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
Mar 27, 2026Wenbo Gao, Renxi Liu, Xian Wang +8LLM Agents LLM Agent Workflow Optimization
Huawei · Hong Kong Polytechnic University
Environment Maps: Structured Environmental Representations for Long-Horizon Agents
Mar 24, 2026Yenchia Feng, Chirag Sharma, Karime MaamariLong-Horizon LLM Agents LLM Agent Planning
Distyl AI
The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
Mar 24, 2026Haoyuan Xu, Chang Li, Xinyan Ma +12LLM Tool Use Long-Horizon LLM Agents
Harbin Institute of Technology, China · Harvard University, USA · Huawei Technologies Co., Ltd., China
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Mar 23, 2026Xixi Wu, Qianguo Sun, Ruiyang Zhang +4Travel Planning RL for Tool Use
The Chinese University of Hong Kong · IDEA Research · University of Macau
Improving Coherence and Persistence in Agentic AI for System Optimization
Mar 22, 2026Pantea Karimi, Kimia Noorbakhsh, Mohammad Alizadeh +1Long-Horizon LLM Agents Autonomous Research Agents
MIT Cambridge, USA
A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
Mar 20, 2026Taiyi Wang, Sian Gooding, Florian Hartmann +2Long-Horizon LLM Agents Web Agents
Google DeepMind
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
Mar 17, 2026Shannan Yan, Jingchen Ni, Leqi Zheng +6LLM Agent Memory Long-Term Conversational Memory
Tsinghua University · WeChat Vision, Tencent Inc.

Apr 16, 2026J/K move · Enter open · S save

Scaling Test-Time Compute for Agentic Coding

Joongwon Kim, Wannan Yang, Kelvin Niu, Hongming Zhang+12

1Meta Superintelligence Labs · University of Washington · 3New York University+4

AI Coding Agents Test-Time Scaling Long-Horizon LLM Agents

Open paper AskPDF arXiv

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this premise: each attempt produces an extended trajectory of actions, observations, errors, and partial progress taken by the agent. In this setting, the main challenge is no longer generating more attempts, but representing prior experience in a form that can be effectively selected from and reused. We propose a test-time scaling framework for agentic coding based on compact representations of rollout trajectories. Our framework converts each rollout into a structured summary that preserves its salient hypotheses, progress, and failure modes while discarding low-signal trace details. This representation enables two complementary forms of inference-time scaling. For parallel scaling, we introduce Recursive Tournament Voting (RTV), which recursively narrows a population of rollout summaries through small-group comparisons. For sequential scaling, we adapt Parallel-Distill-Refine (PDR) to the agentic setting by conditioning new rollouts on summaries distilled from prior attempts. Our method consistently improves the performance of frontier coding agents across SWE-Bench Verified and Terminal-Bench v2.0. For example, by using our method Claude-4.5-Opus improves from 70.9% to 77.6% on SWE-Bench Verified (mini-SWE-agent) and 46.9% to 59.1% on Terminal-Bench v2.0 (Terminus 1). Our results suggest that test-time scaling for long-horizon agents is fundamentally a problem of representation, selection, and reuse.